Skip to content

Simple image classifier microservice using tensorflow and sanic

License

Notifications You must be signed in to change notification settings

gbnk0/simple-image-classifier

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

simple-image-classifier

Simple image classifier microservice using tensorflow

pipeline status dockerbuild Codacy Badge python_version

PREREQUISITES FOR LOCAL RUN

  • A linux system
  • python >= 3.5

QUICKSTART GUIDE

RUN WITH DOCKER
docker run -p8080:8080 gbnk0/simple-image-classifier:latest
LOCAL RUN WITH PYTHON

Go to the app folder:

cd app/
pip3 install -r requirements.txt
python3 app.py

It will listen on localhost:8080

EXAMPLES:

cd example-lib/
edit the example.py file with your set of pictures
python3 example.py

POPULATING DATASET

When you successfully created a dataset using the /datasets endpoint: One method for populating the new dataset is to copy all your categories folders (dog, cat, fish, people) to the data/{datasetName}/labels/ folder.

API DOCUMENTATION:

Run in Postman